© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3488
    Prev
    Next
    INDEX
    Explanations

    measurements in yards associated with football plays

    oai_token-act-pair · gemini-2.0-flash

    Football scores

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     $^{\
    -0.52
    <bos>
    -0.51
    چال
    -0.49
    имущества
    -0.48
     praça
    -0.47
    roek
    -0.46
     fortsatt
    -0.46
    inheritdoc
    -0.46
     PropTypes
    -0.45
     phủ
    -0.45
    POSITIVE LOGITS
    цездатний
    0.75
    WithIOException
    0.69
    IsMutable
    0.64
    AttributeSet
    0.61
    parsedMessage
    0.60
     الحره
    0.59
    XmlAccessType
    0.58
    RuleContext
    0.54
    Cyfeiriadau
    0.54
    adə
    0.54
    Activations Density 0.455%

    No Known Activations